MALT Powers Up Adversarial Attacks
Not on the map. Why?
Abstract (arXiv)
Current adversarial attacks for multi-class classifiers choose the target class for a given input naively, based on the classifier's confidence levels for various target classes. We present a novel adversarial targeting method, textitMALT - Mesoscopic Almost Linearity Targeting, based on medium-scale almost linearity assumptions. Our attack wins over the current state of the art AutoAttack on the standard benchmark datasets CIFAR-100 and ImageNet and for a variety of robust models. In particular, our attack is five times faster than AutoAttack, while successfully matching all of AutoAttack's successes and attacking additional samples that were previously out of reach. We then prove formally and demonstrate empirically that our targeting method, although inspired by linear predictors, also applies to standard non-linear models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 2 Jul 2024.
Builds on
37 of 47 references.
References · 37
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
- 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
25 more
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
- 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
- 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
- 2018Disentangling Adversarial Robustness and Generalizationcited by 171
- 2021A Universal Law of Robustness via Isoperimetrycited by 150
- 2019Adversarial Robustness through Local Linearizationcited by 146
- 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
- 2018Adversarial examples from computational constraintscited by 79
- 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
- 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
- 2018Adversarial vulnerability for any classifiercited by 78
- 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
- 2023Decoupled Kullback-Leibler Divergence Losscited by 58
- 2018On the Geometry of Adversarial Examplescited by 43
- 2021The Dimpled Manifold Model of Adversarial Examples in Machine Learningcited by 41
- 2019A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distancecited by 32
- 2022Gradient Methods Provably Converge to Non-Robust Networkscited by 27
- 2021A single gradient step finds adversarial examples on random two-layers neural networkscited by 26
- 2021Adversarial Examples in Multi-Layer Random ReLU Networkscited by 26
- 2023The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networkscited by 23
- 2022Adversarial Examples in Random Neural Networks with General Activationscited by 13
- 2024Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerabilitycited by 5
- 2019Enforcing Linearity in DNN succours Robustness and Adversarial Image Generationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.